Digital pathology slice automatic focusing method and device based on five-point heterogeneous constraint

By employing a five-point heterogeneous constraint autofocus method, combined with coarse and fine focusing, and layered modeling to compensate for insufficient adaptation in local abnormal areas, the problem of low efficiency in existing technologies is solved, and efficient and clear digital pathological slide scanning is achieved.

CN122018137BActive Publication Date: 2026-06-09SHENZHEN SHENGQIANG TECH
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
SHENZHEN SHENGQIANG TECH
Filing Date
2026-04-10
Publication Date
2026-06-09

AI Technical Summary

Technical Problem

Existing digital pathology slide scanning technology is inefficient when increasing the number of focus points, struggles to adapt to the texture features and focusing reliability differences of different pathological tissue types, and does not fully utilize historical focal plane information in the scanning direction, resulting in repeated modeling of each local area and low efficiency.

Method used

The five-point heterogeneous constraint autofocus method selects five focus points that take into account the overall focal plane reference, scanning direction trend, lateral boundary prediction accuracy, and local focal plane abrupt change compensation between coarse and fine focusing. Layered modeling is used to compensate for the insufficient adaptation of low-order surface fitting to local abnormal regions. Combined with focus confidence, fitting residual and tissue category identification, regions with low focusing reliability are accurately identified and locally corrected.

Benefits of technology

Achieving highly robust and efficient autofocus with a smaller number of focus points, while taking into account both gradual changes in the overall tissue surface and abrupt changes in the local area, improves scanning throughput and imaging clarity, reduces unnecessary fine modeling operations, and enhances scanning efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122018137B_ABST
    Figure CN122018137B_ABST
Patent Text Reader

Abstract

The scheme provides a digital pathological section automatic focusing method and device based on five-point heterogeneous constraints, a low-power objective lens with a lower target magnification is used to obtain a low-power preview image of a target section, and an organization region in the low-power preview image is segmented; coarse focusing is performed on the low-power preview image to obtain a coarse focal surface model; a high-risk region in the coarse focal surface model is divided; fine focusing is performed on each high-risk region to obtain a plurality of fine focal surface models; a focal surface of a non-high-risk region is taken as a first focal surface set, and the fine focal surface models of the high-risk regions are taken as a second focal surface set, and an automatic focusing path of the target section is obtained based on the first focal surface set and the second focal surface set. In the coarse focusing and the fine focusing, five focusing points are selected, which take into account the overall focal surface reference, the scanning direction trend, the lateral boundary prediction accuracy and the local focal surface mutation compensation, so as to make up for the insufficient adaptation of the low-order curved surface fitting to the local abnormal region, and to realize accurate acquisition of the automatic focusing path.
Need to check novelty before this filing date? Find Prior Art